Data to 7 Oct 2026

Domain Generalization by Solving Jigsaw Puzzles

arXiv 1903.06864 ↗First posted 16 Mar 2019cs.CV cs.LGcited by 449

Not on the map. Why?

Abstract (arXiv)

Human adaptability relies crucially on the ability to learn and merge knowledge both from supervised and unsupervised learning: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the task of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals how to solve a jigsaw puzzle on the same images. This secondary task helps the network to learn the concepts of spatial correlation while acting as a regularizer for the classification task. Multiple experiments on the PACS, VLCS, Office-Home and digits datasets confirm our intuition and show that this simple method outperforms previous domain generalization and adaptation solutions. An ablation study further illustrates the inner workings of our approach.

Key facts. Cited by 449 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 130; 2022: 102; 2023: 100; 2024: 52; 2025: 47; 2026: 18.

449 papers.

Sort:

By area:

2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
2021Domain Generalization: A Surveycited by 760
2021Domain Generalization with MixStylecited by 563
2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
2021A Fourier-based Framework for Domain Generalizationcited by 287
2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
2021Gradient Matching for Domain Generalizationcited by 258
2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
2021Learning to Diversify for Single Domain Generalizationcited by 170
2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163

38 more

2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
2021Model-Based Domain Generalizationcited by 103
2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
2023CLIPood: Generalizing CLIP to Out-of-Distributionscited by 96
2021Towards Principled Disentanglement for Domain Generalizationcited by 91
2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
2021Invariant Information Bottleneck for Domain Generalizationcited by 86
2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
2021Adversarially Adaptive Normalization for Single Domain Generalizationcited by 85
2022Self-Supervised Learning for Videos: A Surveycited by 85
2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
2021Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalizationcited by 83
2022My View is the Best View: Procedure Learning from Egocentric Videoscited by 81
2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 76
2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
2021What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?cited by 63
2021Domain Generalization via Gradient Surgerycited by 60
2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 57
2021MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptationcited by 54
2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
2022Prompt Vision Transformer for Domain Generalizationcited by 52
2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
2023Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentationcited by 51
2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
2021Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixingcited by 49
2021Unsupervised Action Segmentation by Joint Representation Learning and Online Clusteringcited by 48

50 most cited of 449 All 449 (JSON)